community pool / model answer
gemma-4-12B-it-GGUF
chat · ggml-org/gemma-4-12B-it-GGUF
57 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB | 4-bit | 57 tok/s | measured | 951 | - GB | 2,048 | llama.cpp |
| RTX 5070 12GB | 4-bit | 72.1 tok/s | reported | 161 | - GB | 2,048 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.